Compare commits
13 Commits
2015.01.01
...
2015.01.02
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
29a9385ff0 | ||
|
|
db546cf87f | ||
|
|
317639758a | ||
|
|
fdbabca85f | ||
|
|
6f790e5821 | ||
|
|
6f5cdeb611 | ||
|
|
9eb4f404cb | ||
|
|
f58487b392 | ||
|
|
772fd5cc44 | ||
|
|
50a0f6df7e | ||
|
|
9f435c5f1c | ||
|
|
931e2d1d26 | ||
|
|
a42419da42 |
1
AUTHORS
1
AUTHORS
@@ -97,3 +97,4 @@ Petr Kutalek
|
||||
Will Glynn
|
||||
Max Reimann
|
||||
Cédric Luthi
|
||||
Thijs Vermeir
|
||||
|
||||
@@ -112,7 +112,7 @@ def _real_main(argv=None):
|
||||
if desc is False:
|
||||
continue
|
||||
if hasattr(ie, 'SEARCH_KEY'):
|
||||
_SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny')
|
||||
_SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
|
||||
_COUNTS = ('', '5', '10', 'all')
|
||||
desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
|
||||
compat_print(desc)
|
||||
|
||||
@@ -71,6 +71,7 @@ from .cnn import (
|
||||
from .collegehumor import CollegeHumorIE
|
||||
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
|
||||
from .comcarcoff import ComCarCoffIE
|
||||
from .commonmistakes import CommonMistakesIE
|
||||
from .condenast import CondeNastIE
|
||||
from .cracked import CrackedIE
|
||||
from .criterion import CriterionIE
|
||||
@@ -473,6 +474,7 @@ from .videott import VideoTtIE
|
||||
from .videoweed import VideoWeedIE
|
||||
from .vidme import VidmeIE
|
||||
from .vidzi import VidziIE
|
||||
from .vier import VierIE, VierVideosIE
|
||||
from .vimeo import (
|
||||
VimeoIE,
|
||||
VimeoAlbumIE,
|
||||
@@ -544,6 +546,7 @@ from .youtube import (
|
||||
YoutubeShowIE,
|
||||
YoutubeSubscriptionsIE,
|
||||
YoutubeTopListIE,
|
||||
YoutubeTruncatedIDIE,
|
||||
YoutubeTruncatedURLIE,
|
||||
YoutubeUserIE,
|
||||
YoutubeWatchLaterIE,
|
||||
|
||||
@@ -10,7 +10,7 @@ from ..compat import compat_HTTPError
|
||||
class BBCCoUkIE(SubtitlesInfoExtractor):
|
||||
IE_NAME = 'bbc.co.uk'
|
||||
IE_DESC = 'BBC iPlayer'
|
||||
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
|
||||
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/(?:episode|playlist))/(?P<id>[\da-z]{8})'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
@@ -84,6 +84,9 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
|
||||
'only_matching': True,
|
||||
}
|
||||
]
|
||||
|
||||
@@ -241,8 +244,8 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
|
||||
|
||||
# fallback to legacy playlist
|
||||
playlist = self._download_xml(
|
||||
'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
|
||||
playlist_id, 'Downloading legacy playlist XML')
|
||||
'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
|
||||
playlist_id, 'Downloading legacy playlist XML')
|
||||
|
||||
no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
|
||||
if no_items is not None:
|
||||
|
||||
29
youtube_dl/extractor/commonmistakes.py
Normal file
29
youtube_dl/extractor/commonmistakes.py
Normal file
@@ -0,0 +1,29 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
|
||||
class CommonMistakesIE(InfoExtractor):
|
||||
IE_DESC = False # Do not list
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:url|URL)
|
||||
'''
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'url',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'URL',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
msg = (
|
||||
'You\'ve asked youtube-dl to download the URL "%s". '
|
||||
'That doesn\'t make any sense. '
|
||||
'Simply remove the parameter in your command or configuration.'
|
||||
) % url
|
||||
if self._downloader.params.get('verbose'):
|
||||
msg += ' Add -v to the command line to see what arguments and configuration youtube-dl got.'
|
||||
raise ExtractorError(msg, expected=True)
|
||||
@@ -905,6 +905,11 @@ class GenericIE(InfoExtractor):
|
||||
return _playlist_from_matches(
|
||||
matches, getter=unescapeHTML, ie='FunnyOrDie')
|
||||
|
||||
# Look for BBC iPlayer embed
|
||||
matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
|
||||
if matches:
|
||||
return self.playlist_result([self.url_result(video_url, ie='BBCCoUk') for video_url in matches])
|
||||
|
||||
# Look for embedded RUTV player
|
||||
rutv_url = RUTVIE._extract_url(webpage)
|
||||
if rutv_url:
|
||||
|
||||
118
youtube_dl/extractor/vier.py
Normal file
118
youtube_dl/extractor/vier.py
Normal file
@@ -0,0 +1,118 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class VierIE(InfoExtractor):
|
||||
IE_NAME = 'vier'
|
||||
_VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
|
||||
'info_dict': {
|
||||
'id': '16129',
|
||||
'display_id': 'het-wordt-warm-de-moestuin',
|
||||
'ext': 'mp4',
|
||||
'title': 'Het wordt warm in De Moestuin',
|
||||
'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.vier.be/video/v3/embed/16129',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
embed_id = mobj.group('embed_id')
|
||||
display_id = mobj.group('display_id') or embed_id
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
video_id = self._search_regex(
|
||||
r'"nid"\s*:\s*"(\d+)"', webpage, 'video id')
|
||||
application = self._search_regex(
|
||||
r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod')
|
||||
filename = self._search_regex(
|
||||
r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename')
|
||||
|
||||
playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename)
|
||||
formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4')
|
||||
|
||||
title = self._og_search_title(webpage, default=display_id)
|
||||
description = self._og_search_description(webpage, default=None)
|
||||
thumbnail = self._og_search_thumbnail(webpage, default=None)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class VierVideosIE(InfoExtractor):
|
||||
IE_NAME = 'vier:videos'
|
||||
_VALID_URL = r'https?://(?:www\.)?vier\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+))?'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.vier.be/demoestuin/videos',
|
||||
'info_dict': {
|
||||
'id': 'demoestuin',
|
||||
},
|
||||
'playlist_mincount': 153,
|
||||
}, {
|
||||
'url': 'http://www.vier.be/demoestuin/videos?page=6',
|
||||
'info_dict': {
|
||||
'id': 'demoestuin-page6',
|
||||
},
|
||||
'playlist_mincount': 20,
|
||||
}, {
|
||||
'url': 'http://www.vier.be/demoestuin/videos?page=7',
|
||||
'info_dict': {
|
||||
'id': 'demoestuin-page7',
|
||||
},
|
||||
'playlist_mincount': 13,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
program = mobj.group('program')
|
||||
|
||||
webpage = self._download_webpage(url, program)
|
||||
|
||||
page_id = mobj.group('page')
|
||||
if page_id:
|
||||
page_id = int(page_id)
|
||||
start_page = page_id
|
||||
last_page = start_page + 1
|
||||
playlist_id = '%s-page%d' % (program, page_id)
|
||||
else:
|
||||
start_page = 0
|
||||
last_page = int(self._search_regex(
|
||||
r'videos\?page=(\d+)">laatste</a>',
|
||||
webpage, 'last page', default=0)) + 1
|
||||
playlist_id = program
|
||||
|
||||
entries = []
|
||||
for current_page_id in range(start_page, last_page):
|
||||
current_page = self._download_webpage(
|
||||
'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
|
||||
program,
|
||||
'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage
|
||||
page_entries = [
|
||||
self.url_result('http://www.vier.be' + video_url, 'Vier')
|
||||
for video_url in re.findall(
|
||||
r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
|
||||
entries.extend(page_entries)
|
||||
|
||||
return self.playlist_result(entries, playlist_id)
|
||||
@@ -1701,3 +1701,20 @@ class YoutubeTruncatedURLIE(InfoExtractor):
|
||||
'"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
|
||||
' or simply youtube-dl BaW_jenozKc .',
|
||||
expected=True)
|
||||
|
||||
|
||||
class YoutubeTruncatedIDIE(InfoExtractor):
|
||||
IE_NAME = 'youtube:truncated_id'
|
||||
IE_DESC = False # Do not list
|
||||
_VALID_URL = r'https?://(?:www\.)youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
raise ExtractorError(
|
||||
'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
|
||||
expected=True)
|
||||
|
||||
@@ -109,7 +109,7 @@ def parseOpts(overrideArguments=None):
|
||||
kw = {
|
||||
'version': __version__,
|
||||
'formatter': fmt,
|
||||
'usage': '%prog [options] url [url...]',
|
||||
'usage': '%prog [OPTIONS] URL [URL...]',
|
||||
'conflict_handler': 'resolve',
|
||||
}
|
||||
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2015.01.01'
|
||||
__version__ = '2015.01.02'
|
||||
|
||||
Reference in New Issue
Block a user